jat

🥈Silver

The World's First Agentic IDE. Visual dashboard: live sessions, task management, code editor, terminal. Epic Swarm parallel workflows. Auto-proceed rules. Automation patterns. Beads + Agent Mail + 50 bash tools. Supervise 20+ agents from one UI.

16010Updated Today

Intermediate30min to implementautomation

Saves ~180 min per use

Quick InstallView Source

git clone https://github.com/joewinke/jat.git

Works with:

Claude

Overview

About This Skill

Setup & Installation

Quick Install

No install command available. Check the GitHub repository for manual installation instructions.

Alternative Install (Git Clone)

git clone https://github.com/joewinke/jat

Requirements

Claude Code or compatible AI agent
Works with: Claude

Quick Start Guide

Install the Skill

Copy the install command above and run it in your terminal.

Open Your AI Agent

Launch Claude Code, Cursor, or your preferred AI coding agent.

Try It Out

Use the prompt template or examples below to test the skill.

Customize

Adapt the skill to your specific use case and workflow.

Usage Examples

Prompt Template

Create a JAT automation workflow for [COMPANY] in the [INDUSTRY] sector. Use [DATA] to generate a parallel workflow that automates [SPECIFIC TASK]. Include auto-proceed rules and at least 3 bash tools from the JAT toolkit.

Example Output

```markdown
## JAT Automation Workflow for GreenTech Solutions

### Workflow Overview
- **Objective**: Automate monthly energy consumption report generation
- **Industry**: Renewable Energy
- **Data Sources**: Smart meters, weather API, internal databases

### Parallel Workflows
1. **Data Collection Workflow**
   - Agent 1: Gather smart meter readings
   - Agent 2: Fetch weather data
   - Agent 3: Extract internal usage data

2. **Data Processing Workflow**
   - Agent 4: Clean and normalize data
   - Agent 5: Apply weather correction algorithms
   - Agent 6: Calculate energy efficiency metrics

3. **Report Generation Workflow**
   - Agent 7: Generate visualizations
   - Agent 8: Compile executive summary
   - Agent 9: Format final report

### Auto-Proceed Rules
- If data collection completes successfully, proceed to processing
- If weather data is unavailable, use 7-day average
- If processing takes longer than 2 hours, notify team lead

### Bash Tools Used
- `jq` for JSON data processing
- `awk` for text pattern scanning
- `bc` for arbitrary precision calculations

### Expected Output
- Automated monthly report in PDF format
- Email notification upon completion
- Dashboard update with key metrics
```